Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “limited memory”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 145 records · Page 8

Nonvolatile read/write memory element - A concept

Memory, with limited number of programming cycles, is achieved by using verticle, fusible links in series with oxide breakthrough elements. Memory elements are fabricated with integrated circuit technology and are ideal for low power digital computer application.

Cricchi, J. R.↗

Shape memory embolectomy devices and systems

An embolectomy device comprised of an expansion unit and a support unit is disclosed. The expansion unit can be actuated in response to one or more external stimuli, and the support unit, located proximately to the expansion unit, provides a force to hold the expansion unit in place and to further induce the expansion unit's radial expansion. The radial expansion of the expansion unit causes the expansion unit to physically contact a blood clot, enabling the blood clot to be removed. In some embodiments, the expansion unit can be fabricated from a shape memory polymer foam. In some embodiments the support unit can be fabricated from any elastic material including, without limitation, shape memory alloys.

Szafron, Jason↗

Shape memory embolectomy devices and systems

An embolectomy device comprised of an expansion unit and a support unit is disclosed. The expansion unit can be actuated in response to one or more external stimuli, and the support unit, located proximately to the expansion unit, provides a force to hold the expansion unit in place and to further induce the expansion unit's radial expansion. The radial expansion of the expansion unit causes the expansion unit to physically contact a blood clot, enabling the blood clot to be removed. In some embodiments, the expansion unit can be fabricated from a shape memory polymer foam. In some embodiments the support unit can be fabricated from any elastic material including, without limitation, shape memory alloys.

59 BASIC BIOLOGICAL SCIENCES↗

Analysis of Vector Particle-In-Cell (VPIC) memory usage optimizations on cutting-edge computer architectures

Vector Particle-In-Cell (VPIC) is one of the fastest plasma simulation codes in the world, with particle numbers ranging from one trillion on the first petascale system, Roadrunner, to ten trillion particles on the more recent Blue Waters supercomputer. As supercomputers continue to grow rapidly in size, so too does the gap between computing capability and memory capability. Current memory systems limit VPIC simulations greatly as the maximum number of particles that can be simulated directly depends on the available memory. In this study, we present a suite of VPIC memory optimizations (i.e., particle weight, half-precision, and fixed-point optimizations) that enable a significant increase in the number of particles in VPIC simulations. Here, we assess the optimizations’ impact on memory and runtime performance for a suite of cutting-edge computer architectures such has the NVIDIA V100 GPU, the IBM Power9, and the Fujitsu A64FX architectures. Our optimizations enable a 31.25% reduction in memory usage and up to 40% increase in the number of particles. This paper extends our work on developing particle storage format optimizations Tan et al.

97 MATHEMATICS AND COMPUTING↗

Confessions of a robot lobotomist

Since its inception, numerically controlled (NC) machining methods have been used throughout the aerospace industry to mill, drill, and turn complex shapes by sequentially stepping through motion programs. However, the recent demand for more precision, faster feeds, exotic sensors, and branching execution have existing computer numerical control (CNC) and distributed numerical control (DNC) systems running at maximum controller capacity. Typical disadvantages of current CNC's include fixed memory capacities, limited communication ports, and the use of multiple control languages. The need to tailor CNC's to meet specific applications, whether it be expanded memory, additional communications, or integrated vision, often requires replacing the original controller supplied with the commercial machine tool with a more powerful and capable system. This paper briefly describes the process and equipment requirements for new controllers and their evolutionary implementation in an aerospace environment. The process of controller retrofit with currently available machines is examined, along with several case studies and their computational and architectural implications.

Gottshall, R. Marc↗

Performance Analysis of Scientific Computing Workloads on Trusted Execution Environments

Scientific computing sometimes involves computation on sensitive data. Depending on the data and the execution environment, the HPC (high-performance computing) user or data provider may require confidentiality and/or integrity guarantees. To study the applicability of hardware-based trusted execution environments (TEEs) to enable secure scientific computing, we deeply analyze the performance impact of AMD SEV and Intel SGX for diverse HPC benchmarks including traditional scientific computing, machine learning, graph analytics, and emerging scientific computing workloads. We observe three main findings: 1) SEV requires careful memory placement on large scale NUMA machines (1x -3.4x slowdown without and 1x -1.15x slowdown with NUMA aware placement), 2) virtualization - a prerequisite for SEV - results in performance degradation for workloads with irregular memory accesses and large working sets (1x -4x slowdown compared to native execution for graph applications) and 3) SGX is inappropriate for HPC given its limited secure memory size and inflexible programming model (1.2x -126x slowdown over unsecure execution). Finally, we discuss forthcoming new TEE designs and their potential impact on scientific computing.

97 MATHEMATICS AND COMPUTING↗

On the Floating Point Performance of the i860 Microprocessor

The i860 microprocessor is a pipelined processor that can deliver two double precision floating point results every clock. It is being used in the Touchstone project to develop a teraflop computer by the year 2000. With such high computational capabilities it was expected that memory bandwidth would limit performance on many kernels. Measured performance of three kernels showed performance is less than what memory bandwidth limitations would predict. This paper develops a model that explains the discrepancy in terms of memory latencies and points to some problems involved in moving data from memory to the arithmetic pipelines.

Lee, King↗

Efficient packing of patterns in sparse distributed memory by selective weighting of input bits

When a set of patterns is stored in a distributed memory, any given storage location participates in the storage of many patterns. From the perspective of any one stored pattern, the other patterns act as noise, and such noise limits the memory's storage capacity. The more similar the retrieval cues for two patterns are, the more the patterns interfere with each other in memory, and the harder it is to separate them on retrieval. A method is described of weighting the retrieval cues to reduce such interference and thus to improve the separability of patterns that have similar cues.

Kanerva, Pentti↗

UltraLiM: In-Memory Boolean Logic Architecture Using UltraRAM

Conventional computing architectures encounter ‘von Neumann’ and ‘memory wall’ bottlenecks which arise due to the back-and-forth data movement between the physically separate memory and processing units and the speed mismatch between them, respectively. These bottlenecks hurt both energy efficiency and the throughput of computing systems. To address these challenges, in-memory computing architectures have emerged as a promising alternative. They reduce the need for frequent data movement by executing different computing tasks inside the memory system. Here, we present UltraLiM, a logic-in-memory architecture using the UltraRAM-based memory system. UltraRAM holds the promise of developing a ‘universal memory’, overcoming the limitations of charge-based memories thanks to their non-volatile behavior with lower operating voltage. This work presents an in-memory computing architecture that integrates an UltraRAM-based memory array with a custom-designed peripheral circuitry. With this architecture, we can perform various in-memory Boolean logic operations (such as NOT, NAND, NOR, and XOR) in a single cycle. Leveraging the separate read-write paths in the UltraRAM-based memory array, we optimize read operations without encountering design conflicts. This optimization enhances the sense margin, enabling the use of simpler peripheral circuitry for in-memory logic operations.

Alam, Shamiul [University of Tennessee, Knoxville ↗

The persistence of a visual dominance effect in a telemanipulator task: A comparison between visual and electrotactile feedback

The possibility to use an electrotactile stimulation in teleoperation and to observe the interpretation of such information as a feedback to the operator was investigated. It is proposed that visual feedback is more informative than an electrotactile one; and that complex electrotactile feedback slows down both the motor decision and motor response processes, is processed as an all or nothing signal, and bypasses the receptive structure and accesses directly in a working memory where information is sequentially processed and where memory is limited in treatment capacity. The electrotactile stimulation is used as an alerting signal. It is suggested that the visual dominance effect is the result of the advantage of both a transfer function and a sensory memory register where information is pretreated and memorized for a short time. It is found that dividing attention has an effect on the acquisition of the information but not on the subsequent decision processes.

Gaillard, J. P.↗

Dynamic memory of a single voltage-gated potassium ion channel: A stochastic nonequilibrium thermodynamic analysis

In this work, we have studied the stochastic response of a single voltage-gated potassium ion channel to a periodic external voltage that keeps the system out-of-equilibrium. The system exhibits memory, resulting from time-dependent driving, that is reflected in terms of dynamic hysteresis in the current-voltage characteristics. The hysteresis loop area has a maximum at some intermediate voltage frequency and disappears in the limits of low and high frequencies. However, the (average) dissipation at long-time limit increases and finally goes to saturation with rising frequency. This raises the question: how diminishing hysteresis can be associated with growing dissipation? To answer this, we have studied the nonequilibrium thermodynamics of the system and analyzed different thermodynamic functions which also exhibit hysteresis. Interestingly, by applying a temporal symmetry analysis in the high-frequency limit, we have analytically shown that hysteresis in some of the periodic responses of the system does not vanish. On the contrary, the rates of free energy and internal energy change of the system as well as the rate of dissipative work done on the system show growing hysteresis with frequency. Hence, although the current-voltage hysteresis disappears in the high-frequency limit, the memory of the ion channel is manifested through its specific nonequilibrium thermodynamic responses.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Concurrent Conditions Access across Validity Intervals in CMSSW

The CMS software system, known as CMSSW, has a generalized conditions, calibration, and geometry data products system called the EventSetup. The EventSetup caches results of reading or calculating data products based on the 'interval of validity', IOV, which is based on the time period for which that data product is appropriate. With the original single threaded CMSSW framework, updating only on an IOV boundary meant we only required memory for a single data product of a given type at any time during the program execution. In 2016 CMS transitioned to using a multithreaded framework as a way to save on memory during processing. This was accomplished by amortizing the memory cost of EventSetup data products across multiple concurrent events. To initially accomplish that goal required synchronizing event processing across IOV boundaries, thereby decreasing the scalability of the system. In this presentation we will explain how we used 'limited concurrent task queues' to allow co ncurrent IOVs while still being able to limit the memory utilized. In addition, we will present performance measurements for both threading scalability of event throughtput and memory utilization.

Dagenhart, W.David↗

Concurrent conditions access across validity intervals in CMSSW

The CMS software system, known as CMSSW, has a generalized conditions, calibration, and geometry data products system called the EventSetup. The EventSetup caches results of reading or calculating data products based on the 'interval of validity', IOV, which is based on the time period for which that data product is appropriate. With the original single threaded CMSSW framework, updating only on an IOV boundary meant we only required memory for a single data product of a given type at any time during the program execution. In 2016 CMS transitioned to using a multi-threaded framework as away to save on memory during processing. This was accomplished by amortizing the memory cost of EventSetup data products across multiple concurrent events. To initially accomplish that goal required synchronizing event processing across IOV boundaries, thereby decreasing the scalability of the system. In this presentation we will explain how we used 'limited concurrent task queues' to allow concurrent IOVs while still being able to limit the memory utilized.

Dagenhart, David↗

Very Large Scale Optimization

The purpose of this research under the NASA Small Business Innovative Research program was to develop algorithms and associated software to solve very large nonlinear, constrained optimization tasks. Key issues included efficiency, reliability, memory, and gradient calculation requirements. This report describes the general optimization problem, ten candidate methods, and detailed evaluations of four candidates. The algorithm chosen for final development is a modern recreation of a 1960s external penalty function method that uses very limited computer memory and computational time. Although of lower efficiency, the new method can solve problems orders of magnitude larger than current methods. The resulting BIGDOT software has been demonstrated on problems with 50,000 variables and about 50,000 active constraints. For unconstrained optimization, it has solved a problem in excess of 135,000 variables. The method includes a technique for solving discrete variable problems that finds a "good" design, although a theoretical optimum cannot be guaranteed. It is very scalable in that the number of function and gradient evaluations does not change significantly with increased problem size. Test cases are provided to demonstrate the efficiency and reliability of the methods and software.

Vanderplaats, Garrett↗

Memory-Efficient Onboard Rock Segmentation

Rockster-MER is an autonomous perception capability that was uploaded to the Mars Exploration Rover Opportunity in December 2009. This software provides the vision front end for a larger software system known as AEGIS (Autonomous Exploration for Gathering Increased Science), which was recently named 2011 NASA Software of the Year. As the first step in AEGIS, Rockster-MER analyzes an image captured by the rover, and detects and automatically identifies the boundary contours of rocks and regions of outcrop present in the scene. This initial segmentation step reduces the data volume from millions of pixels into hundreds (or fewer) of rock contours. Subsequent stages of AEGIS then prioritize the best rocks according to scientist- defined preferences and take high-resolution, follow-up observations. Rockster-MER has performed robustly from the outset on the Mars surface under challenging conditions. Rockster-MER is a specially adapted, embedded version of the original Rockster algorithm ("Rock Segmentation Through Edge Regrouping," (NPO- 44417) Software Tech Briefs, September 2008, p. 25). Although the new version performs the same basic task as the original code, the software has been (1) significantly upgraded to overcome the severe onboard re source limitations (CPU, memory, power, time) and (2) "bulletproofed" through code reviews and extensive testing and profiling to avoid the occurrence of faults. Because of the limited computational power of the RAD6000 flight processor on Opportunity (roughly two orders of magnitude slower than a modern workstation), the algorithm was heavily tuned to improve its speed. Several functional elements of the original algorithm were removed as a result of an extensive cost/benefit analysis conducted on a large set of archived rover images. The algorithm was also required to operate below a stringent 4MB high-water memory ceiling; hence, numerous tricks and strategies were introduced to reduce the memory footprint. Local filtering operations were re-coded to operate on horizontal data stripes across the image. Data types were reduced to smaller sizes where possible. Binary- valued intermediate results were squeezed into a more compact, one-bit-per-pixel representation through bit packing and bit manipulation macros. An estimated 16-fold reduction in memory footprint relative to the original Rockster algorithm was achieved. The resulting memory footprint is less than four times the base image size. Also, memory allocation calls were modified to draw from a static pool and consolidated to reduce memory management overhead and fragmentation. Rockster-MER has now been run onboard Opportunity numerous times as part of AEGIS with exceptional performance. Sample results are available on the AEGIS website at http://aegis.jpl.nasa.gov.

Burl, Michael C.↗

Analog Nonvolatile Computer Memory Circuits

In nonvolatile random-access memory (RAM) circuits of a proposed type, digital data would be stored in analog form in ferroelectric field-effect transistors (FFETs). This type of memory circuit would offer advantages over prior volatile and nonvolatile types: In a conventional complementary metal oxide/semiconductor static RAM, six transistors must be used to store one bit, and storage is volatile in that data are lost when power is turned off. In a conventional dynamic RAM, three transistors must be used to store one bit, and the stored bit must be refreshed every few milliseconds. In contrast, in a RAM according to the proposal, data would be retained when power was turned off, each memory cell would contain only two FFETs, and the cell could store multiple bits (the exact number of bits depending on the specific design). Conventional flash memory circuits afford nonvolatile storage, but they operate at reading and writing times of the order of thousands of conventional computer memory reading and writing times and, hence, are suitable for use only as off-line storage devices. In addition, flash memories cease to function after limited numbers of writing cycles. The proposed memory circuits would not be subject to either of these limitations. Prior developmental nonvolatile ferroelectric memories are limited to one bit per cell, whereas, as stated above, the proposed memories would not be so limited. The design of a memory circuit according to the proposal must reflect the fact that FFET storage is only partly nonvolatile, in that the signal stored in an FFET decays gradually over time. (Retention times of some advanced FFETs exceed ten years.) Instead of storing a single bit of data as either a positively or negatively saturated state in a ferroelectric device, each memory cell according to the proposal would store two values. The two FFETs in each cell would be denoted the storage FFET and the control FFET. The storage FFET would store an analog signal value, between the positive and negative FFET saturation values. This signal value would represent a numerical value of interest corresponding to multiple bits: for example, if the memory circuit were designed to distinguish among 16 different analog values, then each cell could store 4 bits. Simultaneously with writing the signal value in the storage FFET, a negative saturation signal value would be stored in the control FFET. The decay of this control-FFET signal from the saturation value would serve as a model of the decay, for use in regenerating the numerical value of interest from its decaying analog signal value. The memory circuit would include addressing, reading, and writing circuitry that would have features in common with the corresponding parts of other memory circuits, but would also have several distinctive features. The writing circuitry would include a digital-to-analog converter (DAC); the reading circuitry would include an analog-to-digital converter (ADC). For writing a numerical value of interest in a given cell, that cell would be addressed, the saturation value would be written in the control FFET in that cell, and the non-saturation analog value representing the numerical value of interest would be generated by use of the DAC and stored in the storage FFET in that cell. For reading the numerical value of interest stored in a given cell, the cell would be addressed, the ADC would convert the decaying control and storage analog signal values to digital values, and an associated fast digital processing circuit would regenerate the numerical value from digital values.

MacLeod, Todd↗

Thread-level parallelization and optimization of NWChem for the Intel MIC architecture

In the multicore era it was possible to exploit the increase in on-chip parallelism by simply running multiple MPI processes per chip. Unfortunately, manycore processors' greatly increased thread- and data-level parallelism coupled with a reduced memory capacity demand an altogether different approach. In this paper we explore augmenting two NWChem modules, triples correction of the CCSD(T) and Fock matrix construction, with OpenMP in order that they might run efficiently on future manycore architectures. As the next NERSC machine will be a self-hosted Intel MIC (Xeon Phi) based supercomputer, we leverage an existing MIC testbed at NERSC to evaluate our experiments. In order to proxy the fact that future MIC machines will not have a host processor, we run all of our experiments in native mode. We found that while straightforward application of OpenMP to the deep loop nests associated with the tensor contractions of CCSD(T) was sufficient in attaining high performance, significant e ort was required to safely and efeciently thread the TEXAS integral package when constructing the Fock matrix. Ultimately, our new MPI+OpenMP hybrid implementations attain up to 65× better performance for the triples part of the CCSD(T) due in large part to the fact that the limited on-card memory limits the existing MPI implementation to a single process per card. Additionally, we obtain up to 1.6× better performance on Fock matrix constructions when compared with the best MPI implementations running multiple processes per card.

CCSD(T)↗

Thread-Level Parallelization and Optimization of NWChem for the Intel MIC Architecture

In the multicore era it was possible to exploit the increase in on-chip parallelism by simply running multiple MPI processes per chip. Unfortunately, manycore processors' greatly increased thread- and data-level parallelism coupled with a reduced memory capacity demand an altogether different approach. In this paper we explore augmenting two NWChem modules, triples correction of the CCSD(T) and Fock matrix construction, with OpenMP in order that they might run efficiently on future manycore architectures. As the next NERSC machine will be a self-hosted Intel MIC (Xeon Phi) based supercomputer, we leverage an existing MIC testbed at NERSC to evaluate our experiments. In order to proxy the fact that future MIC machines will not have a host processor, we run all of our experiments in tt native mode. We found that while straightforward application of OpenMP to the deep loop nests associated with the tensor contractions of CCSD(T) was sufficient in attaining high performance, significant effort was required to safely and efficiently thread the TEXAS integral package when constructing the Fock matrix. Ultimately, our new MPI OpenMP hybrid implementations attain up to 65x better performance for the triples part of the CCSD(T) due in large part to the fact that the limited on-card memory limits the existing MPI implementation to a single process per card. Additionally, we obtain up to 1.6x better performance on Fock matrix constructions when compared with the best MPI implementations running multiple processes per card.

97 MATHEMATICS AND COMPUTING↗